Volume 04 - Issue 11 (November 2020)


Title: Analysis and prediction of soybean meal price based on uncertain time series
Authors: Hao Sun, Yuanguo Zhu
Source: International Journal of Latest Research in Engineering and Management, pp 01 - 11, Vol 04 - No. 11, 2020
Abstract: The fluctuation of soybean meal futures price has a profound impact on soybean crushing, poulty and livestock breeding and other related enterprises. Based on the uncertainty theory and time series analysis, an uncertain autoregressive moving average model is established. Based on the data of soybean futures main contract price from 2001 to 2016 in Dalian Commodity Exchange of China, we predict the trend of soybean meal future price by the proposed method. The result shows the reliability of the proposed model.
Keywords: ARMA model, prediction, soybean meal futures price, time series, uncertainty theory.
Download Full Article


Title: The Intelligent Fault Diagnosis System Design with Augmented Reality for Electric Motors
Authors: Yu-Ching Lin, Wei-Chih Su, Heng-Chuan Kan, Jian-Ming Lu, Pao-Wen Wang, Yu-Kai Luo, Yu-Chia Liao, Chun-Hui Chung and Mi-Ching Tsai
Source: International Journal of Latest Research in Engineering and Management, pp 12 - 18, Vol 04 - No. 11, 2020
Abstract: With the rapid development of industrial automation technology, electric motors have developed into an important technology in life. However, motor faults have many possible causes, and it is not easy to detect in advance. Therefore, the fault diagnosis technology of motors is an important issue in recent years. Augmented reality (AR) technology has also been rapidly developing in recent years towards various industrial and educational applications. The AR technology is also suitable for the design and fault diagnosis of electric motors. This research is focused on the development and integration of intelligent diagnosis system and AR application for electric motors. The intelligent diagnosis system also applies cloud data management and machine learning methods to predict the health status and the possible abnormalities of electric motors. The time-recurrent Long Short-Term Memory (LSTM) neural network algorithm is applied to establish a motor health diagnostic model. The experimental results show that the motor diagnosis method can predict the health status of motor effectively. The AR technology can also displays the alarm signals of the digital electric motor model on the mobile devices immediately to provide a convenient and efficient management mechanism. The proposed system can also provide more industrial application services in the future.
Keywords: Diagnosis system, Electric motors, Augmented reality, Machine learning, LSTM.
Download Full Article


Title: Crimean-Congo Hemorrhagic Fever (CCHFV) Risk Modeling for Cameroon based on the Spatial Distribution of its Endemic Tick Vectors and Suitability of the Ecological Niche for Purpose of Disease Surveillance
Authors: Lila Reni Bibriven
Source: International Journal of Latest Research in Engineering and Management, pp 19 - 35, Vol 04 - No. 11, 2020
Abstract: Crimean Congo Hemorrhagic Fever Virus (CCHFV) is a severe tick-borne infection mainly transmitted to livestock and humans by ticks of the Nairovirus genus and family Bunyaviridae. This life-threatening pathogen is geographically diverse and found in many parts of the world including West Africa, Asia, and Europe. This tick-borne infection is highly pathogenic and recognized as the most medically important tick-borne disease affecting humans. Modeling the spatial distribution of the tick vectors of thislife-threatening human diseases, is vital to appreciating the ecological determinants of CCHF infections and spread as well as providing a planning framework for CCHFV surveillance and control programs in countries which have not yet experienced major outbreaks such as Cameroon. This research, incorporates the maximum entropy modeling approach (Maxent) to model the risk vulnerability of the local populations across Cameroon to the Crimean Congo hemorrhagic fever virus (CCHFV) by modeling the ecological niche suitability and geo-spatial distribution of CCHFV tick vectors found in the study area. Further, this paper accesses the geospatial distribution of risk, human vulnerability,and ecological niche suitability of eightdifferent CCHFV tick vectors specifically, Amblyomma variegatum,Hyalomma dromedarii, Hyalomma rufipes, Hyalomma truncatum, Rhicephalus sanguineus, Rhipicephalus annulatus, Rhipicephalus decoloratus, Rhipicephalus microplus. Thepreliminary outputs of the model clearly show evidence of CCHFV tick vector geolocation preferences in terms of its ecological niche suitability in Cameroon. The final model resultspresent a foundation and creates a road map for CCHFV surveillance which is vital for health personals monitoring diseases as well as stressing the importance of incorporating geospatial attributes to dynamic diseases surveillance efforts and control programs in Cameroon.
Keywords: Crimean-Congo hemorrhagic fever virus, Ecological niche, Tick vectors, Vulnerability, Spatial distribution, Maxent, Modeling, and Disease surveillance.
Download Full Article